A Markov Decision Process model for patient service sequence policy in digital subtraction angiography treatment

Digital subtraction angiography (DSA) is a technique used in radiology to clearly visualize blood vessels in a bony or dense soft tissue environment. It is widely applied in traumatology department and orthopedics. Usually, the amount of doctors qualified for DSA is limited, so not all the patients in emergency will be treated immediately. Patient's condition may get worse because of treatment delay. Considering this situation, a finite-horizon Markov Decision Process (MDP) model is proposed to solve this problem and improve current service quality in this paper. In this model, the priority for patients to have DSA is discussed when several patients, including patients with reservation and emergency patients, are waiting in the queue for treatment. The model is used to optimize the DSA service sequence policy, which aims to maximize the total rewards. The rewards include treatment rewards and postponing loss of all the patients. Simulation modeling is used to get computational results. Finally, the performance of the optimized policy is compared with the FCFS (first come first served) policy. The postponing loss of patients reduce by 53% and the total rewards of the hospital increase by 58%.